© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 44726
    Prev
    Next
    INDEX
    Explanations

    limit

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .Asset
    -0.09
    bond
    -0.08
     bonds
    -0.08
     bonding
    -0.08
    нында
    -0.08
     bond
    -0.08
    .asset
    -0.08
    eddy
    -0.08
     grime
    -0.08
     electrolyte
    -0.08
    POSITIVE LOGITS
     LIMIT
    0.12
     محدود
    0.10
    (limit
    0.10
     OFFSET
    0.10
     limit
    0.10
    LIMIT
    0.10
    限制
    0.10
    .limit
    0.10
    Limit
    0.09
     limité
    0.09
    Activations Density 0.004%

    No Known Activations